How to choose rental buildings?

# load packages and data
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.0      ✔ stringr 1.4.1 
## ✔ readr   2.1.2      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(plotly)

## Warning: 程辑包'plotly'是用R版本4.2.2 来建造的

## 
## 载入程辑包：'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

load("E:/2023_autumn/DataScience/Final_Proj/data/cleaned_data.RData")
load("E:/2023_autumn/DataScience/Final_Proj/data/Manhattan_latlonmap.RData")

Overview

transformed_rental_income=
  transformed_rental_income %>%
  separate(boro_block_lot, into = c("borough", "block", "lot"), sep = "-") %>%
  mutate(
  borough = case_when(
    borough == "1" ~ "Manhattan",
    borough == "2" ~ "Bronx",
    borough == "3" ~ "Brooklyn",
    borough == "4" ~ "Queens",
    borough == "5" ~ "Staten Island")
  ) %>% 
  filter(
    borough == "Manhattan"
  )

Manhattan_data = Manhattan_data %>%
  separate(address, into = c("address", "toremove"), sep = ",") %>%
  select(-toremove)

transformed_rental_income = 
  left_join(transformed_rental_income, Manhattan_data, by = "address")

## Columbia university lat lon 40.80754 -73.96257
## Hammer health science building lat lon 40.84252 -73.94243 

for_map =  transformed_rental_income %>% 
  filter(report_year > 2019) %>%
  select(-c(latitude,longitude)) 

income_sqft_M = for_map %>%
  plot_mapbox(
    lon = ~lon,
    lat = ~lat,
    color = ~gross_income_per_sq_ft,
    mode = 'markers',
    alpha = 0.5,
    hovertext = ~gross_income_per_sq_ft,
    hoverinfo = 'text',
    colors = "Spectral"
  ) %>%
  layout(
    mapbox = list(
      style = "streets",
      zoom = 10,
      center = list(lat = 40.81, lon = -73.96)
    )
  )

yearsbuild_M = for_map %>%
  plot_mapbox(
    lon = ~lon,
    lat = ~lat,
    color = ~year_built,
    mode = 'markers',
    alpha = 0.5,
    hovertext = ~year_built,
    hoverinfo = 'text',
    colors = c('red','yellow','green')
  ) %>%
  layout(
    mapbox = list(
      style = "streets",
      zoom = 10,
      center = list(lat = 40.81, lon = -73.96)
    )
  )

elevator_M = for_map %>%
  plot_mapbox(
    lon = ~lon,
    lat = ~lat,
    color = ~building_classification,
    mode = 'markers',
    alpha = 1,
    hovertext = ~building_classification,
    hoverinfo = 'text'
  ) %>%
  layout(
    mapbox = list(
      style = "streets",
      zoom = 10,
      center = list(lat = 40.81, lon = -73.96)
    )
  )


subplot(income_sqft_M, yearsbuild_M,elevator_M, nrows = 1, margin = 0.01) %>% layout(showlegend = FALSE, title = 'Income/sqft - Year built - Classification')

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

income_sqft_M

yearsbuild_M

elevator_M

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

text here

Does the building years and building classification related to rental price?

one way anova to test the classification term

for_map %>%
  group_by(building_classification) %>%
  summarise(
    n = n(),
    mean = mean(gross_income_per_sq_ft),
    sum = sum(gross_income_per_sq_ft),
    variance = var(gross_income_per_sq_ft)
  )

## # A tibble: 17 × 5
##    building_classification     n  mean      sum variance
##    <chr>                   <int> <dbl>    <dbl>    <dbl>
##  1 C1-WALK-UP               1476  33.2  49058.     196. 
##  2 C4-WALK-UP               1195  40.8  48767.     144. 
##  3 C5-WALK-UP                366  46.6  17051.      77.3
##  4 C6-WALK-UP               1410  37.7  53185.     183. 
##  5 C7-WALK-UP                960  37.6  36140.     228. 
##  6 C8-WALK-UP                  1  38.0     38.0     NA  
##  7 C9-WALK-UP                  1  55.4     55.4     NA  
##  8 D0-ELEVATOR               265  46.3  12261.      35.4
##  9 D1-ELEVATOR              2553  36.0  91896.     148. 
## 10 D2-ELEVATOR                65  36.0   2342.      69.3
## 11 D3-ELEVATOR              1861  38.7  71938.      81.7
## 12 D4-ELEVATOR              3160  40.4 127553.     110. 
## 13 D5-ELEVATOR               463  45.8  21203.      49.0
## 14 D6-ELEVATOR              2724  45.9 125110.      62.5
## 15 D7-ELEVATOR              1070  39.4  42170      141. 
## 16 D8-ELEVATOR               307  45.5  13958.      59.9
## 17 D9-ELEVATOR               619  43.3  26800.      95.9

for_map %>%
  ggplot(aes(x =building_classification, y = gross_income_per_sq_ft,fill =building_classification))+
  geom_boxplot()+
  theme(
        axis.text.x = element_text(angle = 90)
      )+
  guides(fill=F)

## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

for_anova = for_map %>%
  filter(
  building_classification!= "C8-WALK-UP",
  building_classification!= "C9-WALK-UP"
  )%>%
  select(c(building_classification,gross_income_per_sq_ft))
  
res = lm(gross_income_per_sq_ft ~ factor(building_classification), data = for_anova)
anova(res)

## Analysis of Variance Table
## 
## Response: gross_income_per_sq_ft
##                                    Df  Sum Sq Mean Sq F value    Pr(>F)    
## factor(building_classification)    14  280558 20039.9  162.64 < 2.2e-16 ***
## Residuals                       18479 2276904   123.2                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

SLR to test the years build

lm(gross_income_per_sq_ft ~ year_built, data = for_map) %>%
  summary()

## 
## Call:
## lm(formula = gross_income_per_sq_ft ~ year_built, data = for_map)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -32.293  -6.901   2.249   7.864  42.745 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept) -22.301489   6.192131  -3.602 0.000317 ***
## year_built    0.032274   0.003208  10.060  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 11.73 on 18494 degrees of freedom
## Multiple R-squared:  0.005442,   Adjusted R-squared:  0.005388 
## F-statistic: 101.2 on 1 and 18494 DF,  p-value: < 2.2e-16

For Columbia Students

what about the price in Columbia university and Columbia university Irving medical center?

latCU = 40.80754
lonCU = -73.96257
latCUIMC = 40.84252
lonCUIMC = -73.94243

near_columbia = for_map %>%
  filter(
    lat >  latCU - 0.01,
    lat < latCU + 0.01,
    lon > lonCU -0.005,
    lon < lonCU + 0.005
    ) %>%
  plot_mapbox(
    lon = ~lon,
    lat = ~lat,
    color = ~gross_income_per_sq_ft,
    mode = 'markers',
    alpha = 1,
    hovertext = ~address,
    text = ~gross_income_per_sq_ft,
    meta = ~building_classification,
    hovertemplate = "%{hovertext} <br> %{meta} <br>gross_income_per_sq_ft: %{text}",
    hoverinfo = 'text',
    colors = "Spectral"
  )  %>%
  layout(
    mapbox = list(
      style = "streets",
      zoom = 13,
      center = list(lat = latCU, lon = lonCU)
    )
  )


near_CUIMC = for_map %>% 
  filter(
    lat >  latCUIMC - 0.01,
    lat < latCUIMC + 0.01,
    lon > lonCUIMC -0.005,
    lon < lonCUIMC + 0.005    
  )%>%
  plot_mapbox(
    lon = ~lon,
    lat = ~lat,
    color = ~gross_income_per_sq_ft,
    mode = 'markers',
    alpha = 1,
    hovertext = ~address,
    text = ~gross_income_per_sq_ft,
    meta = ~building_classification,
    hovertemplate = "%{hovertext} <br> %{meta} <br>gross_income_per_sq_ft: %{text}",
    hoverinfo = 'text',
    colors = "Spectral"
  ) %>%
  layout(
    mapbox = list(
      style = "streets",
      zoom = 13,
      center = list(lat = latCUIMC, lon = lonCUIMC)
    )
  )

subplot(near_columbia, near_CUIMC, nrows = 1, titleY = TRUE, titleX = TRUE, margin = 0.01)